Machine Learning Engineer Graduate (E-Commerce Content Recommendation

Team Introduction, You will help build - and rewrite - an industrial recommendation system serving a billion-scale user base across short-video, livestream, and product scenarios, covering retrieval, pre-ranking, ranking, and blending end to end. Every iteration ships to production and directly moves user experience and GMV.

• Scale recommendation models like LLMs. Push ranking models from hundreds of millions to billions of parameters and chart the scaling laws of recommendation: behavior-corpus pretraining; multi-scenario, multi-task, multi-stage joint training; ultra-long behavior-sequence modeling (10K+ events) with KV caching, sequence compression, user/generation (U-G) disaggregated serving, speculative decoding, and dynamic batching - raising MFU while holding a strict millisecond latency budget.
• Build one-stage generative retrieval. Reframe retrieval as generation: tokenize the item space into semantic IDs (RQ-VAE / SID) and train autoregressive models, grounded in MLLM semantics, to generate what a user wants next - collapsing the traditional “multi-channel retrieval + ranking” funnel into a single generative stage. The open problems span the full stack: item tokenizers that balance semantic content against collaborative signal, and SIDs that stay stable while millions of new items arrive daily; post-training the generator directly on live user feedback (preference optimization, GRPO-style RL); and decoding under a millisecond budget - beam search, decoding constrained to the valid item space, and test-time scaling that trades inference compute for better recommendations. The prize is a system freed from its path dependence on ID memorization, where cold-start generalization comes from semantics rather than impression history.
• Inject world knowledge. Use large models’ real-world knowledge to mine latent user interests and semantic representations beyond what pure ID co-occurrence can express; use reasoning models to run explicit chain-of-thought inference over long-horizon user intent, making the system materially better at discovery and novelty.
• Push training and inference to the hardware limit. Custom CUDA / Triton fused kernels, memory and computation-graph optimization, distributed training and inference acceleration, mixed precision and low-bit quantization - engineered for what makes recommendation hard: sparse embeddings, variable-length sequences, and many task heads.
• Rewrite R&D with agents. We are embedding coding agents deep into the algorithm-development loop: automated feature mining and pipeline generation, experiment configuration and training orchestration, automated evaluation and online-diagnosis attribution, bad-case mining and patrol. You will be both a user and a builder of this system.
• Do original work on open problems. Long-term value modeling, repurchase and retention, transaction attribution, fatigue modeling, new-user recommendation, incremental value modeling, interest exploration, LLM4Rec - problems where industry has no standard answers. We expect, and support, original research: internal papers, patents, and publication at top external venues.

Global E-Commerce (TikTok Shop) is one of TikTok’s fastest-growing businesses and a core driver of the company’s revenue growth. Our Global E-Commerce Content Recommendation team owns the end-to-end recommendation stack for e-commerce video and image-text content on TikTok worldwide - retrieval, ranking, and multi-queue blending; supply ecosystem and cold start; and the browsing-to-purchase experience for hundreds of millions of users., Individuals who are completing or have recently completed a PhD degree in Computer Science, AI, Mathematics, Statistics or a related discipline

• Solid ML and engineering fundamentals: you understand the math behind the models, and you write clean, efficient, reproducible code with a strong command of algorithms and data structures.
• Deep research or engineering practice in at least one of: LLMs / foundation models, NLP, CV, RL, or recommendation / search / ads - and you can articulate why you made the choices you made, and where they fell short.
• Genuine enthusiasm for LLM / LRM techniques: you want frontier methods live in production, not parked at offline metrics.
• Strong problem definition and decomposition: faced with an ambiguous problem that has no standard answer, you find your own foothold., Publications at KDD, SIGIR, RecSys, WWW, ACL, NeurIPS, ICML, ICLR, or comparable venues - or high-quality open-source work.
• CUDA / Triton kernel development, source-level deep-learning-framework optimization, large-scale distributed training, or high-performance inference deployment.
• Hands-on experience with LLM post-training (SFT / RLHF / DPO / GRPO), agent-system construction, or inference acceleration.
• Led or deeply contributed to a key project in search, ads, recommendation, or large models, with a complete problem-to-online-impact loop.
• Awards in ACM-ICPC, NOI, Kaggle, or comparable competitions.
• Heavy user of AI coding and agentic workflows for building systems and optimizing models.

The base salary range for this position in the selected city is $153900 - $300960 annually.

Compensation may vary outside of this range depending on a number of factors, including a candidate’s qualifications, skills, competencies and experience, and location. Base pay is one part of the Total Package that is provided to compensate and recognize employees for their work, and this role may be eligible for additional discretionary bonuses/incentives, and restricted stock units.

Benefits may vary depending on the nature of employment and the country work location. Employees have day one access to medical, dental, and vision insurance, a 401(k) savings plan with company match, paid parental leave, short-term and long-term disability coverage, life insurance, wellbeing benefits, among others. Employees also receive 10 paid holidays per year, 10 paid sick days per year and 17 days of Paid Personal Time (prorated upon hire with increasing accruals by tenure).

The Company reserves the right to modify or change these benefits programs at any time, with or without notice.

For Los Angeles County (unincorporated) Candidates:

Qualified applicants with arrest or conviction records will be considered for employment in accordance with all federal, state, and local laws including the Los Angeles County Fair Chance Ordinance for Employers and the California Fair Chance Act. Our company believes that criminal history may have a direct, adverse and negative relationship on the following job duties, potentially resulting in the withdrawal of the conditional offer of employment:

1. Interacting and occasionally having unsupervised contact with internal/external clients and/or colleagues;

2. Appropriately handling and managing confidential information including proprietary and trade secret information and access to information technology systems; and

We believe recommendation is being rewritten in the compute era. ID-based collaborative filtering and supervised learning built today’s systems and still run most of the industry - but their returns are diminishing, and we are betting the next order of magnitude on rebuilding the stack on LLM foundations. Our ambition is to build the most advanced recommendation system in the world, and the next generation after that.